A Novel Online Adaptive Dynamic Programming Algorithm With Adjustable Convergence Rate

Yonghua Wang1; Zheliang Zhang1; Yongwei Zhang2; Mingming Liang1; Derong Liu3

2024

10.1109/TCSI.2023.3346029

IEEE Transactions on Circuits and Systems I: Regular Papers   影响因子和分区

1558-0806

1558-0806

This article develops a novel online adaptive dynamic programming algorithm with adjustable convergence rate to address the optimal control problem of nonlinear systems. Relaxation factors are introduced to tune the convergence rate of value function sequence online. A novel update law based on recursive least squares is developed to adjust the weight of critic neural network at the sampling instant. The uniform ultimate boundedness of the neural network estimation error and the closed-loop system state are analyzed by utilizing the Lyapunov technique. Finally, the effectiveness of the present algorithm is demonstrated by executing three simulation examples.

Adaptive dynamic programming discrete-time nonlinear systems convergence rate online optimal control neural networks

SCI ; EI

英语

其他

ENGINEERING

2-s2.0-85182356156

IEEE

1.School of Automation, Guangdong University of Technology, Guangzhou, China
2.College of Mathematics and Informatics, South China Agricultural University, Guangzhou, China
3.School of System Design and Intelligent Manufacturing, Southern University of Science and Technology, Shenzhen, China

Yonghua Wang,Zheliang Zhang,Yongwei Zhang,et al. A Novel Online Adaptive Dynamic Programming Algorithm With Adjustable Convergence Rate[J]. IEEE Transactions on Circuits and Systems I: Regular Papers,2024,PP(99):1-14.

Yonghua Wang,Zheliang Zhang,Yongwei Zhang,Mingming Liang,&Derong Liu.(2024).A Novel Online Adaptive Dynamic Programming Algorithm With Adjustable Convergence Rate.IEEE Transactions on Circuits and Systems I: Regular Papers,PP(99),1-14.

Yonghua Wang,et al."A Novel Online Adaptive Dynamic Programming Algorithm With Adjustable Convergence Rate".IEEE Transactions on Circuits and Systems I: Regular Papers PP.99(2024):1-14.